{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3FNOVHN5MNX6NDA37XMHFT4QOR","short_pith_number":"pith:3FNOVHN5","schema_version":"1.0","canonical_sha256":"d95aea9dbd636fe68c1bfdd872cf90746388cc064ed7c332178e12d216411b93","source":{"kind":"arxiv","id":"2408.12320","version":3},"attestation_state":"computed","paper":{"title":"TensorOpera Router: A Multi-Model Router for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alay Dilipbhai Shah, Chaoyang He, Dimitris Stripelis, Han Jin, Jipeng Zhang, Salman Avestimehr, Yuhang Yao, Zhaozhuo Xu, Zijian Hu","submitted_at":"2024-08-22T11:57:07Z","abstract_excerpt":"With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present TO-Router, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.12320","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T11:57:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"80ad584c3b2c919a113d532383ad7fe6481247f8dd4db1c14d711ba29fd3a542","abstract_canon_sha256":"bd58496577934628e43c90a60b5f5859a67e1b452df372efe00aacaca6029a1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:00.789503Z","signature_b64":"FdYLVpy8ebRpDYY0o8n9g897p4TRXRenWfcD4zc3P6pVVaCt/1mLkpl35lq+ZSelLE38e/+Qo2uCSf4Daad8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d95aea9dbd636fe68c1bfdd872cf90746388cc064ed7c332178e12d216411b93","last_reissued_at":"2026-07-05T09:25:00.788979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:00.788979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorOpera Router: A Multi-Model Router for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alay Dilipbhai Shah, Chaoyang He, Dimitris Stripelis, Han Jin, Jipeng Zhang, Salman Avestimehr, Yuhang Yao, Zhaozhuo Xu, Zijian Hu","submitted_at":"2024-08-22T11:57:07Z","abstract_excerpt":"With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present TO-Router, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12320","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.12320/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.12320","created_at":"2026-07-05T09:25:00.789039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12320v3","created_at":"2026-07-05T09:25:00.789039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12320","created_at":"2026-07-05T09:25:00.789039+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FNOVHN5MNX6","created_at":"2026-07-05T09:25:00.789039+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FNOVHN5MNX6NDA3","created_at":"2026-07-05T09:25:00.789039+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FNOVHN5","created_at":"2026-07-05T09:25:00.789039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00053","citing_title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06098","citing_title":"IR3DE: A Linear Router for Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12601","citing_title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07112","citing_title":"Switchcraft: AI Model Router for Agentic Tool Calling","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR","json":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR.json","graph_json":"https://pith.science/api/pith-number/3FNOVHN5MNX6NDA37XMHFT4QOR/graph.json","events_json":"https://pith.science/api/pith-number/3FNOVHN5MNX6NDA37XMHFT4QOR/events.json","paper":"https://pith.science/paper/3FNOVHN5"},"agent_actions":{"view_html":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR","download_json":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR.json","view_paper":"https://pith.science/paper/3FNOVHN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12320&json=true","fetch_graph":"https://pith.science/api/pith-number/3FNOVHN5MNX6NDA37XMHFT4QOR/graph.json","fetch_events":"https://pith.science/api/pith-number/3FNOVHN5MNX6NDA37XMHFT4QOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR/action/storage_attestation","attest_author":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR/action/author_attestation","sign_citation":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR/action/citation_signature","submit_replication":"https://pith.science/pith/3FNOVHN5MNX6NDA37XMHFT4QOR/action/replication_record"}},"created_at":"2026-07-05T09:25:00.789039+00:00","updated_at":"2026-07-05T09:25:00.789039+00:00"}